基于强化学习混合集成模型的风速预测:新疆高速铁路强风信号预测研究

IF 2.7 4区 工程技术 Q2 TRANSPORTATION SCIENCE & TECHNOLOGY
B. Liu, Xinmin Pan, Rui Yang, Zhu Duan, Ye Li, Shi Yin, N. Nikitas, Hui Liu
{"title":"基于强化学习混合集成模型的风速预测:新疆高速铁路强风信号预测研究","authors":"B. Liu, Xinmin Pan, Rui Yang, Zhu Duan, Ye Li, Shi Yin, N. Nikitas, Hui Liu","doi":"10.1093/tse/tdac064","DOIUrl":null,"url":null,"abstract":"\n Considering the application of wind forecasting technology along the railway, it becomes an effective means to reduce the risk of train derailment and overturning. Accurate prediction of crosswinds can provide scientific guidance for safe train operation. To obtain more reliable wind speed prediction results, this study proposes an intelligent ensemble forecasting method for strong winds along the high-speed railway. The method consists of three parts, including data preprocessing module, hybrid prediction module, and reinforcement learning ensemble module. First, fast ensemble empirical model decomposition (FEEMD) is used to process the original wind speed data. Then, broyden-fletcher-goldfarb-shanno (BFGS), non-linear autoregressive network with exogenous inputs (NARX), and deep belief network (DBN), three benchmark predictors with different characteristics, are employed to build prediction models for all the sublayers of decomposition. Finally, Q-learning is utilized to iteratively calculate the combined weights of the three models, and the prediction results of each sublayer are superimposed to obtain the model output. The real wind speed data of two Railway stations in Xinjiang are used for experimental comparison. Experiments show that compared with the single benchmark model, the hybrid ensemble model has better accuracy and robustness for wind speed prediction along the railway. The 1-step forecasting results mean absolute error (MAE), mean absolute percentage error (MAPE), and root mean square error (RMSE) of Q-learning-FEEMD-BFGS-NARX-DBN in site #1 and site #2 are 0.0894 m/s, 0.6509%, 0.1146 m/s, and 0.0458 m/s, 0.2709%, 0.0616 m/s. The proposed ensemble model is a promising method for railway wind speed prediction.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":null,"pages":null},"PeriodicalIF":2.7000,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Forecasting wind speed using a reinforcement learning hybrid ensemble model: a high-speed railways strong wind signal prediction study in Xinjiang, China\",\"authors\":\"B. Liu, Xinmin Pan, Rui Yang, Zhu Duan, Ye Li, Shi Yin, N. Nikitas, Hui Liu\",\"doi\":\"10.1093/tse/tdac064\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"\\n Considering the application of wind forecasting technology along the railway, it becomes an effective means to reduce the risk of train derailment and overturning. Accurate prediction of crosswinds can provide scientific guidance for safe train operation. To obtain more reliable wind speed prediction results, this study proposes an intelligent ensemble forecasting method for strong winds along the high-speed railway. The method consists of three parts, including data preprocessing module, hybrid prediction module, and reinforcement learning ensemble module. First, fast ensemble empirical model decomposition (FEEMD) is used to process the original wind speed data. Then, broyden-fletcher-goldfarb-shanno (BFGS), non-linear autoregressive network with exogenous inputs (NARX), and deep belief network (DBN), three benchmark predictors with different characteristics, are employed to build prediction models for all the sublayers of decomposition. Finally, Q-learning is utilized to iteratively calculate the combined weights of the three models, and the prediction results of each sublayer are superimposed to obtain the model output. The real wind speed data of two Railway stations in Xinjiang are used for experimental comparison. Experiments show that compared with the single benchmark model, the hybrid ensemble model has better accuracy and robustness for wind speed prediction along the railway. The 1-step forecasting results mean absolute error (MAE), mean absolute percentage error (MAPE), and root mean square error (RMSE) of Q-learning-FEEMD-BFGS-NARX-DBN in site #1 and site #2 are 0.0894 m/s, 0.6509%, 0.1146 m/s, and 0.0458 m/s, 0.2709%, 0.0616 m/s. The proposed ensemble model is a promising method for railway wind speed prediction.\",\"PeriodicalId\":52804,\"journal\":{\"name\":\"Transportation Safety and Environment\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.7000,\"publicationDate\":\"2022-12-21\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Transportation Safety and Environment\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1093/tse/tdac064\",\"RegionNum\":4,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"TRANSPORTATION SCIENCE & TECHNOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Transportation Safety and Environment","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1093/tse/tdac064","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"TRANSPORTATION SCIENCE & TECHNOLOGY","Score":null,"Total":0}
引用次数: 0

摘要

考虑到风预报技术在铁路沿线的应用,它成为降低列车脱轨和倾覆风险的有效手段。准确预测侧风,可为列车安全运行提供科学指导。为了获得更可靠的风速预测结果,本研究提出了一种高速铁路沿线强风的智能综合预测方法。该方法由三部分组成,包括数据预处理模块、混合预测模块和强化学习集成模块。首先,使用快速集合经验模型分解(FEEMD)对原始风速数据进行处理。然后,采用broyden-fletcher-goldfarb-shanno(BFGS)、具有外生输入的非线性自回归网络(NARX)和深度信念网络(DBN)这三个具有不同特征的基准预测因子,为分解的所有子层建立预测模型。最后,利用Q学习迭代计算三个模型的组合权重,并将每个子层的预测结果叠加以获得模型输出。利用新疆两个火车站的实际风速数据进行了实验比较。实验表明,与单一基准模型相比,混合集成模型对铁路沿线风速预测具有更好的准确性和鲁棒性。Q-learning-FEEMD-BFGS-NARX-DBN在#1和#2站点的一步预测结果的平均绝对误差(MAE)、平均绝对百分比误差(MAPE)和均方根误差(RMSE)分别为0.0894m/s、0.6509%、0.1146m/s和0.0458m/s、0.2709%、0.0616m/s。所提出的集合模型是一种很有前途的铁路风速预测方法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Forecasting wind speed using a reinforcement learning hybrid ensemble model: a high-speed railways strong wind signal prediction study in Xinjiang, China
Considering the application of wind forecasting technology along the railway, it becomes an effective means to reduce the risk of train derailment and overturning. Accurate prediction of crosswinds can provide scientific guidance for safe train operation. To obtain more reliable wind speed prediction results, this study proposes an intelligent ensemble forecasting method for strong winds along the high-speed railway. The method consists of three parts, including data preprocessing module, hybrid prediction module, and reinforcement learning ensemble module. First, fast ensemble empirical model decomposition (FEEMD) is used to process the original wind speed data. Then, broyden-fletcher-goldfarb-shanno (BFGS), non-linear autoregressive network with exogenous inputs (NARX), and deep belief network (DBN), three benchmark predictors with different characteristics, are employed to build prediction models for all the sublayers of decomposition. Finally, Q-learning is utilized to iteratively calculate the combined weights of the three models, and the prediction results of each sublayer are superimposed to obtain the model output. The real wind speed data of two Railway stations in Xinjiang are used for experimental comparison. Experiments show that compared with the single benchmark model, the hybrid ensemble model has better accuracy and robustness for wind speed prediction along the railway. The 1-step forecasting results mean absolute error (MAE), mean absolute percentage error (MAPE), and root mean square error (RMSE) of Q-learning-FEEMD-BFGS-NARX-DBN in site #1 and site #2 are 0.0894 m/s, 0.6509%, 0.1146 m/s, and 0.0458 m/s, 0.2709%, 0.0616 m/s. The proposed ensemble model is a promising method for railway wind speed prediction.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Transportation Safety and Environment
Transportation Safety and Environment TRANSPORTATION SCIENCE & TECHNOLOGY-
CiteScore
3.90
自引率
13.60%
发文量
32
审稿时长
10 weeks
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信